Back to Details

firecrawl-scrape

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Firecrawl Scrape Skill

Firecrawl 网页抓取技能

When to Use

使用场景

  • Scrape content from any URL
  • Extract structured data from web pages
  • Search the web and get content
  • 从任意URL抓取内容
  • 从网页提取结构化数据
  • 搜索网页并获取内容

Instructions

使用说明

bash
uv run python -m runtime.harness scripts/mcp/firecrawl_scrape.py \
    --url "https://example.com" \
    --format "markdown"
bash
uv run python -m runtime.harness scripts/mcp/firecrawl_scrape.py \
    --url "https://example.com" \
    --format "markdown"

Parameters

参数说明

  • --url
    : URL to scrape
  • --format
    : Output format - 
    markdown
    , 
    html
    , 
    text
    (default: markdown)
  • --search
    : (alternative) Search query instead of direct URL
  • --url
    : 要抓取的URL
  • --format
    : 输出格式 - 
    markdown
    , 
    html
    , 
    text
    （默认值：markdown）
  • --search
    : （替代选项）使用搜索查询而非直接URL

Examples

示例

bash
undefined
bash
undefined

Scrape a page

Scrape a page

uv run python -m runtime.harness scripts/mcp/firecrawl_scrape.py
--url "https://docs.python.org/3/library/asyncio.html"
uv run python -m runtime.harness scripts/mcp/firecrawl_scrape.py
--url "https://docs.python.org/3/library/asyncio.html"

Search and scrape

Search and scrape

uv run python -m runtime.harness scripts/mcp/firecrawl_scrape.py
--search "Python asyncio best practices 2024"
undefined
uv run python -m runtime.harness scripts/mcp/firecrawl_scrape.py
--search "Python asyncio best practices 2024"
undefined

MCP Server Required

需配置MCP服务器

Requires 
firecrawl
server in mcp_config.json with FIRECRAWL_API_KEY.
需要在mcp_config.json中配置带有FIRECRAWL_API_KEY的
firecrawl
服务器。